|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [xen stable-4.16] xen/sched: migrate timers to correct cpus after suspend
commit 1dc6dccb1a8752f200ec2612b2bd091bbf88b231
Author: Juergen Gross <jgross@xxxxxxxx>
AuthorDate: Wed Nov 9 11:00:04 2022 +0100
Commit: Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Wed Nov 9 11:00:04 2022 +0100
xen/sched: migrate timers to correct cpus after suspend
Today all timers are migrated to cpu 0 when the system is being
suspended. They are not migrated back after resuming the system again.
This results (at least) to visible problems with the credit scheduler,
as the timer isn't handled on the cpu it was expected to occur, which
will result in an ASSERT() triggering. Other more subtle problems, like
uninterrupted elongated time slices, are probable. The least effect
will be worse performance on cpu 0 resulting from most scheduling
related timer interrupts happening there after suspend/resume.
Add migrating the scheduling related timers of a specific cpu from cpu
0 back to its original cpu when that cpu has gone up when resuming the
system.
Fixes: 0763cd268789 ("xen/sched: don't disable scheduler on cpus during
suspend")
Signed-off-by: Juergen Gross <jgross@xxxxxxxx>
Tested-by: Marek Marczykowski-Górecki <marmarek@xxxxxxxxxxxxxxxxxxxxxx>
Acked-by: Dario Faggioli <dfaggioli@xxxxxxxx>
master commit: 37f82facd62f720fdcec104f72f86b8c6c214820
master date: 2022-11-04 09:03:23 +0100
---
xen/common/sched/core.c | 29 +++++++++++++++++++++++
xen/common/sched/cpupool.c | 2 ++
xen/common/sched/credit.c | 13 +++++++++++
xen/common/sched/private.h | 10 ++++++++
xen/common/sched/rt.c | 58 ++++++++++++++++++++++++++++++++--------------
5 files changed, 94 insertions(+), 18 deletions(-)
diff --git a/xen/common/sched/core.c b/xen/common/sched/core.c
index 9173cf690c..03ace41540 100644
--- a/xen/common/sched/core.c
+++ b/xen/common/sched/core.c
@@ -1284,6 +1284,35 @@ static int cpu_disable_scheduler_check(unsigned int cpu)
return 0;
}
+/*
+ * Called after a cpu has come up again in a suspend/resume cycle.
+ * Migrate all timers for this cpu (they have been migrated to cpu 0 when the
+ * cpu was going down).
+ * Note that only timers related to a physical cpu are migrated, not the ones
+ * related to a vcpu or domain.
+ */
+void sched_migrate_timers(unsigned int cpu)
+{
+ struct sched_resource *sr;
+
+ rcu_read_lock(&sched_res_rculock);
+
+ sr = get_sched_res(cpu);
+
+ /*
+ * Note that on a system with parked cpus (e.g. smt=0 on Intel cpus) this
+ * will be called for the parked cpus, too, so the case for no scheduling
+ * resource being available must be considered.
+ */
+ if ( sr && sr->master_cpu == cpu )
+ {
+ migrate_timer(&sr->s_timer, cpu);
+ sched_move_timers(sr->scheduler, sr);
+ }
+
+ rcu_read_unlock(&sched_res_rculock);
+}
+
/*
* In general, this must be called with the scheduler lock held, because the
* adjust_affinity hook may want to modify the vCPU state. However, when the
diff --git a/xen/common/sched/cpupool.c b/xen/common/sched/cpupool.c
index b5a948639a..a083c5a3c6 100644
--- a/xen/common/sched/cpupool.c
+++ b/xen/common/sched/cpupool.c
@@ -1022,6 +1022,8 @@ static int cpu_callback(
case CPU_ONLINE:
if ( system_state <= SYS_STATE_active )
rc = cpupool_cpu_add(cpu);
+ else
+ sched_migrate_timers(cpu);
break;
case CPU_DOWN_PREPARE:
/* Suspend/Resume don't change assignments of cpus to cpupools. */
diff --git a/xen/common/sched/credit.c b/xen/common/sched/credit.c
index d0aa017c64..a432a7e000 100644
--- a/xen/common/sched/credit.c
+++ b/xen/common/sched/credit.c
@@ -614,6 +614,18 @@ init_pdata(struct csched_private *prv, struct csched_pcpu
*spc, int cpu)
spc->nr_runnable = 0;
}
+static void
+csched_move_timers(const struct scheduler *ops, struct sched_resource *sr)
+{
+ struct csched_private *prv = CSCHED_PRIV(ops);
+ struct csched_pcpu *spc = sr->sched_priv;
+
+ if ( sr->master_cpu == prv->master )
+ migrate_timer(&prv->master_ticker, prv->master);
+
+ migrate_timer(&spc->ticker, sr->master_cpu);
+}
+
/* Change the scheduler of cpu to us (Credit). */
static spinlock_t *
csched_switch_sched(struct scheduler *new_ops, unsigned int cpu,
@@ -2267,6 +2279,7 @@ static const struct scheduler sched_credit_def = {
.switch_sched = csched_switch_sched,
.alloc_domdata = csched_alloc_domdata,
.free_domdata = csched_free_domdata,
+ .move_timers = csched_move_timers,
};
REGISTER_SCHEDULER(sched_credit_def);
diff --git a/xen/common/sched/private.h b/xen/common/sched/private.h
index 0126a4bb9e..0527a8c70d 100644
--- a/xen/common/sched/private.h
+++ b/xen/common/sched/private.h
@@ -331,6 +331,8 @@ struct scheduler {
struct xen_sysctl_scheduler_op *);
void (*dump_settings) (const struct scheduler *);
void (*dump_cpu_state) (const struct scheduler *, int);
+ void (*move_timers) (const struct scheduler *,
+ struct sched_resource *);
};
static inline int sched_init(struct scheduler *s)
@@ -485,6 +487,13 @@ static inline int sched_adjust_cpupool(const struct
scheduler *s,
return s->adjust_global ? s->adjust_global(s, op) : 0;
}
+static inline void sched_move_timers(const struct scheduler *s,
+ struct sched_resource *sr)
+{
+ if ( s->move_timers )
+ s->move_timers(s, sr);
+}
+
static inline void sched_unit_pause_nosync(const struct sched_unit *unit)
{
struct vcpu *v;
@@ -622,6 +631,7 @@ struct cpu_rm_data *alloc_cpu_rm_data(unsigned int cpu,
bool aff_alloc);
void free_cpu_rm_data(struct cpu_rm_data *mem, unsigned int cpu);
int schedule_cpu_rm(unsigned int cpu, struct cpu_rm_data *mem);
int sched_move_domain(struct domain *d, struct cpupool *c);
+void sched_migrate_timers(unsigned int cpu);
struct cpupool *cpupool_get_by_id(unsigned int poolid);
void cpupool_put(struct cpupool *pool);
int cpupool_add_domain(struct domain *d, unsigned int poolid);
diff --git a/xen/common/sched/rt.c b/xen/common/sched/rt.c
index ec2ca1bebc..fd62ddc0d5 100644
--- a/xen/common/sched/rt.c
+++ b/xen/common/sched/rt.c
@@ -750,6 +750,27 @@ rt_switch_sched(struct scheduler *new_ops, unsigned int
cpu,
return &prv->lock;
}
+static void move_repl_timer(struct rt_private *prv, unsigned int old_cpu)
+{
+ cpumask_t *online = get_sched_res(old_cpu)->cpupool->res_valid;
+ unsigned int new_cpu = cpumask_cycle(old_cpu, online);
+
+ /*
+ * Make sure the timer run on one of the cpus that are still available
+ * to this scheduler. If there aren't any left, it means it's the time
+ * to just kill it.
+ */
+ if ( new_cpu >= nr_cpu_ids )
+ {
+ kill_timer(&prv->repl_timer);
+ dprintk(XENLOG_DEBUG, "RTDS: timer killed on cpu %d\n", old_cpu);
+ }
+ else
+ {
+ migrate_timer(&prv->repl_timer, new_cpu);
+ }
+}
+
static void
rt_deinit_pdata(const struct scheduler *ops, void *pcpu, int cpu)
{
@@ -759,25 +780,25 @@ rt_deinit_pdata(const struct scheduler *ops, void *pcpu,
int cpu)
spin_lock_irqsave(&prv->lock, flags);
if ( prv->repl_timer.cpu == cpu )
- {
- cpumask_t *online = get_sched_res(cpu)->cpupool->res_valid;
- unsigned int new_cpu = cpumask_cycle(cpu, online);
+ move_repl_timer(prv, cpu);
- /*
- * Make sure the timer run on one of the cpus that are still available
- * to this scheduler. If there aren't any left, it means it's the time
- * to just kill it.
- */
- if ( new_cpu >= nr_cpu_ids )
- {
- kill_timer(&prv->repl_timer);
- dprintk(XENLOG_DEBUG, "RTDS: timer killed on cpu %d\n", cpu);
- }
- else
- {
- migrate_timer(&prv->repl_timer, new_cpu);
- }
- }
+ spin_unlock_irqrestore(&prv->lock, flags);
+}
+
+static void
+rt_move_timers(const struct scheduler *ops, struct sched_resource *sr)
+{
+ unsigned long flags;
+ struct rt_private *prv = rt_priv(ops);
+ unsigned int old_cpu;
+
+ spin_lock_irqsave(&prv->lock, flags);
+
+ old_cpu = prv->repl_timer.cpu;
+ if ( prv->repl_timer.status != TIMER_STATUS_invalid &&
+ prv->repl_timer.status != TIMER_STATUS_killed &&
+ !cpumask_test_cpu(old_cpu, sr->cpupool->res_valid) )
+ move_repl_timer(prv, old_cpu);
spin_unlock_irqrestore(&prv->lock, flags);
}
@@ -1555,6 +1576,7 @@ static const struct scheduler sched_rtds_def = {
.sleep = rt_unit_sleep,
.wake = rt_unit_wake,
.context_saved = rt_context_saved,
+ .move_timers = rt_move_timers,
};
REGISTER_SCHEDULER(sched_rtds_def);
--
generated by git-patchbot for /home/xen/git/xen.git#stable-4.16
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |